Title :
Systolic devices for speech processing
Author :
Beresford-Smith, B. ; Breckling, J. ; Schröder, H.
Author_Institution :
Comput. Sci. Lab., Australian Nat. Univ., Canberra, ACT, Australia
Abstract :
A frequently used method of representing words in the area of speech recognition is as a sequence of LPC (linear prediction coefficient) vectors, which are real-valued 12- to 16-dimensional vectors each representing a time slice of the speech signal. It can be associated with particular phonems (or transitions between phonems). One method of transferring speech in a real-time environment is through the use of codebooks; i.e. a set of representatives of LPC vectors. The method proposed is based on the following idea: a sequence of N LPC vectors is produced out of a few minutes of speech. Then a distance matrix is calculated using any suitable distance function such as the Itakura distance. Then this distance matrix can be analyzed by repeatedly looking for rows with a maximal number of small-valued entries. These rows refer to clusters in the LPC vector space and thus can be assumed to be good representatives to be used as members of the codebook
Keywords :
cellular arrays; speech analysis and processing; speech recognition; Itakura distance; clusters; codebooks; distance matrix; linear prediction coefficient vectors; real-time environment; speech processing; speech recognition; systolic devices; Australia; Clustering algorithms; Computer science; Hardware; Hidden Markov models; Laboratories; Speech analysis; Speech processing; Speech recognition; Vector quantization;
Conference_Titel :
CompEuro '89., 'VLSI and Computer Peripherals. VLSI and Microelectronic Applications in Intelligent Peripherals and their Interconnection Networks', Proceedings.
Conference_Location :
Hamburg
Print_ISBN :
0-8186-1940-6
DOI :
10.1109/CMPEUR.1989.93379
